© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 151609
    Prev
    Next
    INDEX
    Explanations

    0800 phone numbers

    np_acts-logits-general · gemini-2.5-flash-lite

    language concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    t
    0.68
    tik
    0.65
    ti
    0.57
    v
    0.55
    ne
    0.55
    tm
    0.55
    tors
    0.55
    tl
    0.53
    ங்கள்
    0.53
    т
    0.52
    POSITIVE LOGITS
     সম্পূর্ণরূপে
    0.50
     potpuno
    0.47
     Quảng
    0.45
     সাফল্যের
    0.43
     कार्या
    0.43
     প্রত্যাখ্যান
    0.43
     영화
    0.42
     পরবর্তীতে
    0.42
     কৃতজ্ঞ
    0.42
     শুরুর
    0.41
    Activations Density 0.005%

    No Known Activations